A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms

Coskun, Damla; Karaboga, Dervis; Basturk, Alper; Basturk Akay, Bahriye; Nalbantoglu, Ozkan Ufuk; DOGAN, SERAP; Pacal, Ishak; Karagöz, Meryem Altın

doi:10.55730/1300-0632.4048

A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms

Damla COŞKUN, (Erciyes Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Kayseri, Türkiye)

Derviş KARABOĞA, (Erciyes Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Kayseri, Türkiye)

Alper BAŞTÜRK, (Erciyes Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Kayseri, Türkiye)

Bahriye AKAY, (Erciyes Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Kayseri, Türkiye)

Özkan Ufuk NALBANTOĞLU, (Erciyes Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Kayseri, Türkiye)

Serap DOĞAN, (Erciyes Üniversitesi, Tıp Fakültesi, Radyoloji Anabilim Dalı, Kayseri, Türkiye)

İshak PAÇAL, (Erciyes Üniversitesi, Yapay Zeka ve Büyük Veri Uygulama ve Araştırma Merkezi, Kayseri, Türkiye)

Meryem Altin KARAGÖZ (Erciyes Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümü, Kayseri, Türkiye)

Turkish Journal of Electrical Engineering and Computer Sciences

17 0

Yıl: 2023 Cilt: 31 Sayı: 7 Sayfa Aralığı: 1294 - 1313 Metin Dili: İngilizce DOI: 10.55730/1300-0632.4048 İndeks Tarihi: 17-01-2024

A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms

Öz:

Breast cancer is a prevalent form of cancer across the globe, and if it is not diagnosed at an early stage it can be life-threatening. In order to aid in its diagnosis, detection, and classification, computer-aided detection (CAD) systems are employed. You Only Look Once (YOLO)-based CAD algorithms have become very popular owing to their highly accurate results for object detection tasks in recent years. Therefore, the most popular YOLO models are implemented to compare the performance in mass detection with various experiments on the INbreast dataset. In addition, a YOLO model with an integrated Swin Transformer in its backbone is proposed for mass detection in mammography images within the study. The performance of YOLOv5 models and a transformer-based YOLO model is compared to that of each other and YOLOv3 and YOLOv4 models using images with different sizes on the INbreast dataset. The best results are obtained by the transformer-based YOLO model of YOLOv5 for 832 × 832 image size. In another experiment, we compared the default anchors against the anchors provided by the YOLOv5 autoanchor function before training and saw that the anchors generated by the YOLOv5 autoanchor increased the success rates. Furthermore, various experiments were conducted to observe how data augmentation affects performance. Although a small amount of data was used in the study, high performance was obtained by YOLO algorithms, which are promising tools for cancer detection.

Anahtar Kelime: Breast cancer deep learning YOLO computer-aided detection transformer-based YOLO data augmen- tation

Belge Türü: Makale Makale Türü: Araştırma Makalesi Erişim Türü: Erişime Açık

[1] Arnold M, Morgan E, Rumgay H, Mafra A, Singh D et al. Current and future burden of breast cancer: global statistics for 2020 and 2040. The Breast 2022; 66: 15-23. https://doi.org/10.1016/J.BREAST.2022.08.010
[2] Siegel RL, Miller KD, Wagle NS, Jemal A. Cancer statistics, 2023. CA: a cancer journal for clinicians 2023; 73 (1): 17-48. https://doi.org/10.3322/CAAC.21763
[3] Parsa P, Kandiah M, Abdul Rahman H, Mohd Zulkefli NA. Barriers for breast cancer screening among Asian women: a mini literature review. Asian Pacific Journal of Cancer Prevention 2006; 7 (4): 509-514.
[4] Gøtzsche PC, Jørgensen KJ. Screening for breast cancer with mammography. Cochrane database of systematic reviews. 2013; (6). https://doi.org/10.1002/14651858.CD001877.pub5
[5] Domingues I, Pereira G, Martins P, Duarte H, Santos J et al. Using deep learning techniques in medical imag- ing: a systematic review of applications on CT and PET. Artificial Intelligence Review 2020; 53: 4093-4160. https://doi.org/10.1007/S10462-019-09788-3
[6] Moghbel M, Mashohor S. A review of computer assisted detection/diagnosis (CAD) in breast thermography for breast cancer detection. Artificial Intelligence Review 2013; 39: 305-313. https://doi.org/10.1007/S10462-011-9274- 2
[7] Veta M, Pluim JPW, van Diest PJ, Viergever MA. Breast cancer histopathology image analysis: a review. IEEE Trans Biomed Eng, 2014; 61 (5): 1400. https://doi.org/10.1109/TBME.2014.2303852
[8] Kozegar E, Soryani M, Behnam H, Salamati M, Tan T. Computer aided detection in automated 3-D breast ultrasound images: a survey. Artificial Intelligence Review 2020; 53: 1919-1941. https://doi.org/10.1007/S10462- 019-09722-7
[9] Shah SM, Khan RA, Arif S, Sajid U. Artificial intelligence for breast cancer analysis: trends & directions. Computers in Biology and Medicine 2022; 105221. https://doi.org/10.1016/J.COMPBIOMED.2022.105221
[10] Li Y, Chen H, Cao L, Ma J. A survey of computer-aided detection of breast cancer with mammography. J Health Med Inf 2016; 4 (7): 1-6. https://doi.org/10.4172/2157-7420.1000238
[11] Liberman L, Menell JH. Breast imaging reporting and data system (BI-RADS). Radiologic Clinics 2002; 40 (3): 409-430. https://doi.org/10.1016/S0033-8389(01)00017-3
[12] Abdelhafiz D, Yang C, Ammar R, Nabavi S. Deep convolutional neural networks for mammography: advances, challenges and applications. BMC Bioinformatics 2019; 20: 1-20. https://doi.org/10.1186/s12859-019-2823-4
[13] Aly GH, Marey M, El-Sayed SA, Tolba MF. YOLO based breast masses detection and classification in full-field digital mammograms. Computer Methods and Programs in Biomedicine 2021; 200: 105823. https://doi.org/10.1016/j.cmpb.2020.105823
[14] Ribli D, Horváth A, Unger Z, Pollner P, Csabai I. Detecting and classifying lesions in mammograms with deep learning. Scientific Reports 2018; 8 (1): 4165.
[15] Peng J, Bao C, Hu C, Wang X, Jian W et al. Automated mammographic mass detection using deformable convolution and multiscale features. Medical & Biological Engineering & Computing 2020; 58: 1405-1417.
[16] Al-masni MA, Al-antari MA, Park JM, Gi G, Kim TY et al. Detection and classification of the breast ab- normalities in digital mammograms via regional convolutional neural network. In: 2017 39th Annual Interna- tional Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, 2017; 1230-1233. https://doi.org/10.1109/EMBC.2017.8037053
[17] Al-Antari MA, Al-Masni MA, Choi MT, Han SM, Kim TS. A fully integrated computer-aided diagnosis system for digital X-ray mammograms via deep learning detection, segmentation, and classification. International Journal of Medical Informatics 2018; 117: 44-54.
[18] Al-Masni MA, Al-Antari MA, Park JM, Gi G, Kim TY et al. Simultaneous detection and classification of breast masses in digital mammograms via a deep learning YOLO-based CAD system. Computer Methods and Programs in Biomedicine 2018; 157: 85-94.
[19] Al-Antari MA, Al-Masni MA, Kim TS. Deep learning computer-aided diagnosis for breast lesion in digital mam- mogram. Deep Learning in Medical Image Analysis: Challenges and Applications 2020; 59-72.
[20] Al-Antari MA, Han SM, Kim TS. Evaluation of deep learning detection and classification towards computer-aided diagnosis of breast lesions in digital X-ray mammograms. Computer Methods and Programs in Biomedicine 2020; 196: 105584.
[21] Djebbar K, Mimi M, Berradja K, Taleb-Ahmed A. Deep convolutional neural networks for detection and classifica- tion of tumors in mammograms. In: IEEE 2019 6th International Conference on Image and Signal Processing and Their Applications (ISPA), 2019. pp. 1-7.
[22] Baccouche A, Garcia-Zapirain B, Olea CC, Elmaghraby AS. Breast lesions detection and classification via YOLO- based fusion models. Computers, Materials & Continua 2021; 69 (1).
[23] Baccouche A, Garcia-Zapirain B, Zheng Y, Elmaghraby AS. Early detection and classification of abnormality in prior mammograms using image-to-image translation and YOLO techniques. Computer Methods and Programs in Biomedicine 2022; 221: 106884.
[24] Hamed G, Marey M, Amin SE, Tolba MF. Automated breast cancer detection and classification in full field digital mammograms using two full and cropped detection paths approach. IEEE Access 2021; 9: 116898-116913.
[25] Zhao J, Chen T, Cai B. A computer-aided diagnostic system for mammograms based on YOLOv3. Multimedia Tools and Applications 2022; 1-25. https://doi.org/10.1007/s11042-021-10505-y
[26] Kolchev A, Pasynkov D, Egoshin I, Kliouchkin I, Pasynkova O et al. YOLOv4-based CNN model versus nested contours algorithm in the suspicious lesion detection on the mammography image: a direct comparison in the real clinical settings. Journal of Imaging 2022; 8 (4): 88.
[27] Yasir N, Anwar S, Khan MT. Machine vision-based intelligent breast cancer detection. Pakistan Journal of Engi- neering and Technology 2022; 5 (1): 1-10.
[28] Hassan NM, Hamad S, Mahar K. A deep learning model for mammography mass detection using mosaic and reconstructed multichannel images. In: International Conference on Computational Science and Its Applications, 2022, (pp. 544-559). Cham: Springer International Publishing.
[29] Zhang L, Li Y, Chen H, Wu W, Chen K et al. Anchor-free YOLOv3 for mass detection in mammogram. Expert Systems with Applications 2022; 191: 116273.
[30] Su Y, Liu Q, Xie W, Hu P. YOLO-LOGO: a transformer-based YOLO segmentation model for breast mass detection and segmentation in digital mammograms. Computer Methods and Programs in Biomedicine 2022; 221: 106903. https://doi.org/10.1016/j.cmpb.2022.106903
[31] Betancourt Tarifa AS, Marrocco C, Molinara M, Tortorella F, Bria A. Transformer-based mass detection in digital mammograms. Journal of Ambient Intelligence and Humanized Computing 2023; 14 (3): 2723-2737.
[32] Kamran SA, Hossain KF, Tavakkoli A, Bebis G, Baker S. Swin-sftnet: spatial feature expansion and aggregation using swin transformer for whole breast micro-mass segmentation, 2022. arXiv preprint arXiv:2211.08717.
[33] Chen X, Zhang K, Abdoli N, Gilley PW, Wang X et al. Transformers improve breast cancer diagnosis from unregistered multi-view mammograms. Diagnostics 2022; 12 (7): 1549.
[34] Lu S, Liu X, He Z, Zhang X, Liu W et al. Swin-Transformer-YOLOv5 for real-time wine grape bunch detection. Remote Sensing 2022; 14 (22): 5853.
[35] Yang W, Wu H, Tang C, Lv J. ST-CA YOLOv5: Improved YOLOv5 based on Swin Transformer and coordinate attention for surface defect detection. In: IEEE 2023 International Joint Conference on Neural Networks (IJCNN) 2023. pp. 1-8.
[36] Vasanthi P, Mohan L. Multi-Head-Self-Attention based YOLOv5X-transformer for multi-scale object detection. Multimedia Tools and Applications 2023; 1-27.
[37] Thuan D. Evolution of YOLO algorithm and YOLOv5: the state-of-the-art object detention algorithm. MA, Oulu University of Applied Sciences, Finland, 2021.
[38] Redmon J, Divvala S, Girshick R, Farhadi A. You Only Look Once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 2016, pp. 779-788. https://doi.org/10.1109/CVPR.2016.91
[39] Redmon J, Farhadi A. YOLO9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017, pp. 6517-6525. https://doi.org/10.1109/CVPR.2017.690
[40] Redmon J, Farhadi A. Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767, 2018. https://doi.org/10.48550/arxiv.1804.02767
[41] Bochkovskiy A, Wang CY, Liao MH. YOLOv4: optimal speed and accuracy of object detection. arXiv 2020, arXiv:2004.10934. https://doi.org/10.48550/arXiv.2004.10934
[42] Wang CY, Mark Liao HY, Wu YH, Chen PY, Hsieh JW et al. CSPNet: a new backbone that can enhance learning capability of CNN. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, 2020, pp. 1571-1580. https://doi.org/10.1109/CVPRW50498.2020.00203
[43] Liu S, Qi L, Qin H, Shi J, Jia J. Path aggregation network for instance segmentation. In: Pro- ceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018; pp. 8759-8768. https://doi.org/10.48550/arXiv.1803.01534
[44] Dlužnevskij D, Stefanovič P, Ramanauskaite S. Investigation of YOLOv5 eﬀiciency in iPhone supported systems. Baltic Journal of Modern Computing 2021; 9.3: 333-344. https://doi.org/10.22364/bjmc.2021.9.3.07
[45] Liu H, Sun F, Gu J, Deng L. SF-YOLOv5: A lightweight small object detection algorithm based on improved feature fusion mode. Sensors 2022; 22 (15): 5817. https://doi.org/10.3390/s22155817
[46] Xue Z, Lin H, Wang F. A small target forest fire detection model based on YOLOv5 improvement. Forests 2022; 13 (8): 1332. https://doi.org/10.3390/f13081332
[47] Chen PY, Hsieh JW, Gochoo M, Wang CY, Liao HYM. Smaller object detection for real-time embedded traﬀic flow estimation using fish-eye cameras. In: 2019 IEEE International Conference on Image Processing (ICIP). 2019. pp. 2956-2960.
[48] Liu Z, Lin Y, Cao Y, Hu H, Wei Y et al. Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE/CVF International Conference on Computer Vision 2021. pp. 10012-10022.
[49] Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X et al. An image is worth 16x16 words: transformers for image recognition at scale, 2020. arXiv preprint arXiv:2010.11929.
[50] Liu Z, Hu H, Lin Y, Yao Z, Xie Z et al. Swin transformer v2: scaling up capacity and resolution. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022. pp. 12009-12019.
[51] Wei Y, Hu H, Xie Z, Zhang Z, Cao Y et al. Contrastive learning rivals masked image modeling in fine-tuning via feature distillation, 2022. arXiv preprint arXiv:2205.14141
[52] Li F, Zhang H, Xu H, Liu S, Zhang L et al. Mask dino: towards a unified transformer-based framework for object detection and segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023. pp. 3041-3050.
[53] Hassan NM, Hamad S, Mahar K. Mammogram breast cancer CAD systems for mass detection and classification: a review. Multimedia Tools and Applications 2022; 81 (14): 20043-20075. https://doi.org/10.1007/s11042-022-12332-1
[54] Dhungel N, Carneiro G, Bradley AP. A deep learning approach for the analysis of masses in mammograms with minimal user intervention. Med Image Anal 2017; 37: 114-128. https://doi.org/10.1016/j.media.2017.01.009
[55] Moreira IC, Amaral I, Domingues I, Cardoso A, Cardoso MJ et al. INbreast: toward a full-field digital mammo- graphic database. Acad Radiol 2012; 19 (2): 236-248. https://doi.org/10.1016/j.acra.2011.09.014

APA	Coskun D, Karaboga D, Basturk A, Basturk Akay B, Nalbantoglu O, DOGAN S, Pacal I, Karagöz M (2023). A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms. , 1294 - 1313. 10.55730/1300-0632.4048
Chicago	Coskun Damla,Karaboga Dervis,Basturk Alper,Basturk Akay Bahriye,Nalbantoglu Ozkan Ufuk,DOGAN SERAP,Pacal Ishak,Karagöz Meryem Altın A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms. (2023): 1294 - 1313. 10.55730/1300-0632.4048
MLA	Coskun Damla,Karaboga Dervis,Basturk Alper,Basturk Akay Bahriye,Nalbantoglu Ozkan Ufuk,DOGAN SERAP,Pacal Ishak,Karagöz Meryem Altın A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms. , 2023, ss.1294 - 1313. 10.55730/1300-0632.4048
AMA	Coskun D,Karaboga D,Basturk A,Basturk Akay B,Nalbantoglu O,DOGAN S,Pacal I,Karagöz M A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms. . 2023; 1294 - 1313. 10.55730/1300-0632.4048
Vancouver	Coskun D,Karaboga D,Basturk A,Basturk Akay B,Nalbantoglu O,DOGAN S,Pacal I,Karagöz M A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms. . 2023; 1294 - 1313. 10.55730/1300-0632.4048
IEEE	Coskun D,Karaboga D,Basturk A,Basturk Akay B,Nalbantoglu O,DOGAN S,Pacal I,Karagöz M "A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms." , ss.1294 - 1313, 2023. 10.55730/1300-0632.4048
ISNAD	Coskun, Damla vd. "A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms". (2023), 1294-1313. https://doi.org/10.55730/1300-0632.4048

APA	Coskun D, Karaboga D, Basturk A, Basturk Akay B, Nalbantoglu O, DOGAN S, Pacal I, Karagöz M (2023). A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms. Turkish Journal of Electrical Engineering and Computer Sciences, 31(7), 1294 - 1313. 10.55730/1300-0632.4048
Chicago	Coskun Damla,Karaboga Dervis,Basturk Alper,Basturk Akay Bahriye,Nalbantoglu Ozkan Ufuk,DOGAN SERAP,Pacal Ishak,Karagöz Meryem Altın A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms. Turkish Journal of Electrical Engineering and Computer Sciences 31, no.7 (2023): 1294 - 1313. 10.55730/1300-0632.4048
MLA	Coskun Damla,Karaboga Dervis,Basturk Alper,Basturk Akay Bahriye,Nalbantoglu Ozkan Ufuk,DOGAN SERAP,Pacal Ishak,Karagöz Meryem Altın A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms. Turkish Journal of Electrical Engineering and Computer Sciences, vol.31, no.7, 2023, ss.1294 - 1313. 10.55730/1300-0632.4048
AMA	Coskun D,Karaboga D,Basturk A,Basturk Akay B,Nalbantoglu O,DOGAN S,Pacal I,Karagöz M A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms. Turkish Journal of Electrical Engineering and Computer Sciences. 2023; 31(7): 1294 - 1313. 10.55730/1300-0632.4048
Vancouver	Coskun D,Karaboga D,Basturk A,Basturk Akay B,Nalbantoglu O,DOGAN S,Pacal I,Karagöz M A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms. Turkish Journal of Electrical Engineering and Computer Sciences. 2023; 31(7): 1294 - 1313. 10.55730/1300-0632.4048
IEEE	Coskun D,Karaboga D,Basturk A,Basturk Akay B,Nalbantoglu O,DOGAN S,Pacal I,Karagöz M "A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms." Turkish Journal of Electrical Engineering and Computer Sciences, 31, ss.1294 - 1313, 2023. 10.55730/1300-0632.4048
ISNAD	Coskun, Damla vd. "A comparative study of YOLO models and a transformer-based YOLOv5 model for mass detection in mammograms". Turkish Journal of Electrical Engineering and Computer Sciences 31/7 (2023), 1294-1313. https://doi.org/10.55730/1300-0632.4048