Meng Jiang1, Di Zhang2, Shi-Chu Tang3, Xiao-Mao Luo4, Zhi-Rui Chuan4, Wen-Zhi Lv5, Fan Jiang6, Xue-Jun Ni2, Xin-Wu Cui7, Christoph F Dietrich8. 1. Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, No. 1095 Jiefang Avenue, Wuhan, 430030, Hubei Province, China. 2. Department of Medical Ultrasound, Affiliated Hospital of Nantong University, Nantong, China. 3. Department of Medical Ultrasound, Hunan Cancer Hospital/The Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, Changsha, 410013, Hunan, China. 4. Department of Medical Ultrasound, Yunnan Cancer Hospital & The Third Affiliated Hospital of Kunming Medical University, Kunming, 650118, China. 5. Department of Artificial Intelligence, Julei Technology Company, Wuhan, 430030, China. 6. Department of Ultrasound, The Second Affiliated Hospital of Anhui Medical University, Hefei, China. 7. Department of Medical Ultrasound, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, No. 1095 Jiefang Avenue, Wuhan, 430030, Hubei Province, China. cuixinwu@live.cn. 8. Department of Internal Medicine, Hirslanden Clinic, Schänzlihalde 11, 3013, Bern, Switzerland.
Abstract
OBJECTIVES: To evaluate the prediction performance of deep convolutional neural network (DCNN) based on ultrasound (US) images for the assessment of breast cancer molecular subtypes. METHODS: A dataset of 4828 US images from 1275 patients with primary breast cancer were used as the training samples. DCNN models were constructed primarily to predict the four St. Gallen molecular subtypes and secondarily to identify luminal disease from non-luminal disease based on the ground truth from immunohistochemical of whole tumor surgical specimen. US images from two other institutions were retained as independent test sets to validate the system. The models' performance was analyzed using per-class accuracy, positive predictive value (PPV), and Matthews correlation coefficient (MCC). RESULTS: The model achieved good performance in identifying the four breast cancer molecular subtypes in the two test sets, with accuracy ranging from 80.07% (95% CI, 76.49-83.23%) to 97.02% (95% CI, 95.22-98.16%) and 87.94% (95% CI, 85.08-90.31%) to 98.83% (95% CI, 97.60-99.43) for the two test cohorts for each sub-category, respectively. In terms of 4-class weighted average MCC, the model achieved 0.59 for test cohort A and 0.79 for test cohort B. Specifically, the DCNN also yielded good diagnostic performance in discriminating luminal disease from non-luminal disease, with a PPV of 93.29% (95% CI, 90.63-95.23%) and 88.21% (95% CI, 85.12-90.73%) for the two test cohorts, respectively. CONCLUSION: Using pretreatment US images of the breast cancer, deep learning model enables the assessment of molecular subtypes with high diagnostic accuracy. TRIAL REGISTRATION: Clinical trial number: ChiCTR1900027676 KEY POINTS: • Deep convolutional neural network (DCNN) helps clinicians assess tumor features with accuracy. • Multicenter retrospective study shows that DCNN derived from pretreatment ultrasound imagine improves the prediction of breast cancer molecular subtypes. • Management of patients becomes more precise based on the DCNN model.
OBJECTIVES: To evaluate the prediction performance of deep convolutional neural network (DCNN) based on ultrasound (US) images for the assessment of breast cancer molecular subtypes. METHODS: A dataset of 4828 US images from 1275 patients with primary breast cancer were used as the training samples. DCNN models were constructed primarily to predict the four St. Gallen molecular subtypes and secondarily to identify luminal disease from non-luminal disease based on the ground truth from immunohistochemical of whole tumor surgical specimen. US images from two other institutions were retained as independent test sets to validate the system. The models' performance was analyzed using per-class accuracy, positive predictive value (PPV), and Matthews correlation coefficient (MCC). RESULTS: The model achieved good performance in identifying the four breast cancer molecular subtypes in the two test sets, with accuracy ranging from 80.07% (95% CI, 76.49-83.23%) to 97.02% (95% CI, 95.22-98.16%) and 87.94% (95% CI, 85.08-90.31%) to 98.83% (95% CI, 97.60-99.43) for the two test cohorts for each sub-category, respectively. In terms of 4-class weighted average MCC, the model achieved 0.59 for test cohort A and 0.79 for test cohort B. Specifically, the DCNN also yielded good diagnostic performance in discriminating luminal disease from non-luminal disease, with a PPV of 93.29% (95% CI, 90.63-95.23%) and 88.21% (95% CI, 85.12-90.73%) for the two test cohorts, respectively. CONCLUSION: Using pretreatment US images of the breast cancer, deep learning model enables the assessment of molecular subtypes with high diagnostic accuracy. TRIAL REGISTRATION: Clinical trial number: ChiCTR1900027676 KEY POINTS: • Deep convolutional neural network (DCNN) helps clinicians assess tumor features with accuracy. • Multicenter retrospective study shows that DCNN derived from pretreatment ultrasound imagine improves the prediction of breast cancer molecular subtypes. • Management of patients becomes more precise based on the DCNN model.
Entities:
Keywords:
Breast cancer; Deep convolutional neural network; Molecular subtype; Ultrasound
Authors: T Sørlie; C M Perou; R Tibshirani; T Aas; S Geisler; H Johnsen; T Hastie; M B Eisen; M van de Rijn; S S Jeffrey; T Thorsen; H Quist; J C Matese; P O Brown; D Botstein; P E Lønning; A L Børresen-Dale Journal: Proc Natl Acad Sci U S A Date: 2001-09-11 Impact factor: 11.205
Authors: Aleix Prat; Maggie Chon U Cheang; Miguel Martín; Joel S Parker; Eva Carrasco; Rosalía Caballero; Scott Tyldesley; Karen Gelmon; Philip S Bernard; Torsten O Nielsen; Charles M Perou Journal: J Clin Oncol Date: 2012-12-10 Impact factor: 44.544
Authors: Daniel E Spratt; Michael J Evans; Brian J Davis; Michael G Doran; Man Xia Lee; Neel Shah; John Wongvipat; Kathryn E Carnazza; George G Klee; William Polkinghorn; Donald J Tindall; Jason S Lewis; Charles L Sawyers Journal: Cancer Res Date: 2015-10-02 Impact factor: 12.701
Authors: Luciano G Martelotto; Charlotte K Y Ng; Salvatore Piscuoglio; Britta Weigelt; Jorge S Reis-Filho Journal: Breast Cancer Res Date: 2014-05-20 Impact factor: 6.466