RESUMEN
OBJECTIVES: To assess the performance of an artificial intelligence (AI) algorithm in the Australian mammography screening program which routinely uses two independent readers with arbitration of discordant results. METHODS: A total of 7533 prevalent round mammograms from 2017 were available for analysis. The AI program classified mammograms into deciles on the basis of breast cancer (BC) risk. BC diagnoses, including invasive BC (IBC) and ductal carcinoma in situ (DCIS), included those from the prevalent round, interval cancers, and cancers identified in the subsequent screening round two years later. Performance was assessed by sensitivity, specificity, positive and negative predictive values, and the proportion of women recalled by the radiologists and identified as higher risk by AI. RESULTS: Radiologists identified 54 women with IBC and 13 with DCIS with a recall rate of 9.7%. In contrast, 51 of 54 of the IBCs and 12/13 cases of DCIS were within the higher AI score group (score 10), a recall equivalent of 10.6% (a difference of 0.9% (CI -0.03 to 1.89%, p = 0.06). When IBCs were identified in the 2017 round, interval cancers classified as false negatives or with minimal signs in 2017, and cancers from the 2019 round were combined, the radiologists identified 54/67 and 59/67 were in the highest risk AI category (sensitivity 80.6% and 88.06 % respectively, a difference that was not different statistically). CONCLUSIONS: As the performance of AI was comparable to that of expert radiologists, future AI roles in screening could include replacing one reader and supporting arbitration, reducing workload and false positive results. CLINICAL RELEVANCE STATEMENT: AI analysis of consecutive prevalent screening mammograms from the Australian BreastScreen program demonstrated the algorithm's ability to match the cancer detection of experienced radiologists, additionally identifying five interval cancers (false negatives), and the majority of the false positive recalls. KEY POINTS: ⢠The AI program was almost as sensitive as the radiologists in terms of identifying prevalent lesions (51/54 for invasive breast cancer, 63/67 when including ductal carcinoma in situ). ⢠If selected interval cancers and cancers identified in the subsequent screening round were included, the AI program identified more cancers than the radiologists (59/67 compared with 54/67, sensitivity 88.06 % and 80.6% respectively p = 0.24). ⢠The high negative predictive value of a score of 1-9 would indicate a role for AI as a triage tool to reduce the recall rate (specifically false positives).
RESUMEN
OBJECTIVE: To assess accuracy of and interobserver agreement on multiparametric MR findings to distinguish uterine leiomyoma (LM) from uterine leiomyosarcoma (LMS) and soft tissue tumour of unknown malignant potential. METHODS: Inclusion criteria: All females over 18 years with least one uterine mass measuring 5 cm or more in at least one of the three standard orthogonal dimensions on MR with histopathological confirmation of LM, LMS, or soft tissue tumour of unknown malignant potential (STUMP) in the 3 months following MR. Patients with LMS were drawn from a larger cohort being assessed for MR-guided focussed ultrasound (MRgFUS) suitability. Image evaluation: Assessed variables were: lesion margin, margin definition, T2 signal homogeneity, >50% of lesion with T2 signal brighter than myometrium, haemorrhage, restricted diffusion, contrast enhancement (CE), CE pattern, local lymphadenopathy and ascites. RESULTS: 32 LM, 10 LMS and 1 STUMP were evaluated. Ill-defined (p-value = 0.0003-0.0004) or irregular (p = 0.003-0.004) lesion margin, T2 hyperintensity >50% (p = 0.001-0.004), and peripheral CE (p = 0.02-0.05) were significantly more common in LMS/STUMP than LM for both radiologists. 10/11 (Reader 2) and 11/11 (Reader 1) LMS/STUMP displayed restricted diffusion but so did 63-80% of LM. Agreement was greatest for margin characteristics (κ = 0.73-0.81). CONCLUSION: Irregular/ill-defined lesion margin best distinguished LMS/STUMP from LM with good interrater reliability. ADVANCES IN KNOWLEDGE: Assessment of agreement regarding MR parameters distinguishing LM from LMS and STUMP has not previously been undertaken in a cohort including a large number of patients with LMS. This will help inform evaluation of females considering minimally invasive LM treatment.
