Predicting ipsilateral recurrence in women treated for ductal carcinoma in situ using machine learning and multivariable logistic regression models.

PURPOSE: To develop machine learning (ML) and multivariable regression models to predict ipsilateral breast event (IBE) risk after ductal carcinoma in situ (DCIS) treatment. METHODS: A retrospective investigation was conducted of patients diagnosed with DCIS from 2007 to 2014 who were followed for a minimum of five years after treatment. Data about each patient were extracted from the medical records. Two ML models (penalized logistic regression and random forest) and a multivariable logistic regression model were developed to evaluate recurrence-related variables. RESULTS: 650 women (mean age 56 years, range 27-87 years) underwent treatment for DCIS and were followed for at least five years after treatment (mean 8.0 years). 5.5% (n = 36) experienced an IBE. With multivariable analysis, the variables associated with higher IBE risk were younger age (adjusted odds ratio [aOR] 0.96, p = 0.02), dense breasts at mammography (aOR 3.02, p = 0.02), and < 5 years of endocrine therapy (aOR 4.48, p = 0.02). The multivariable regression model to predict IBE risk achieved an area under the receiver operating characteristic curve (AUC) of 0.75 (95% CI 0.67-0.84). The penalized logistic regression and random forest models achieved mean AUCs of 0.52 (95% CI 0.42-0.61) and 0.54 (95% CI 0.43-0.65), respectively. CONCLUSION: Variables associated with higher IBE risk after DCIS treatment include younger age, dense breasts, and <5 years of adjuvant endocrine therapy. The multivariable logistic regression model attained the highest AUC (0.75), suggesting that regression models have a critical role in risk prediction for patients with DCIS.

Contralateral breast cancer after curative-intent treatment for ductal carcinoma in situ: Rate and associated clinicopathological and imaging risk factors.

PURPOSE: Patients who have ductal carcinoma in situ (DCIS) are undergoing bilateral mastectomy at increasing rates. One of the reasons is to minimize contralateral breast cancer (CBC) risk. The purpose of this study is to determine the rate of and risk factors associated with CBC in women treated for DCIS. METHODS: A retrospective study was performed of women with DCIS at surgery from 2007 to 2014 who had at least five-year follow-up. Patient attributes, imaging findings, histopathology results, and surgical and long-term outcomes were collected. Features associated with a CBC were assessed with multivariable logistic regression models. RESULTS: 613 women (mean 56 years, range 30-87) with DCIS underwent breast-conserving surgery (BCS) (n = 426), unilateral mastectomy (n = 101), or bilateral mastectomy (n = 86), with mean follow-up of 7.9 years. Of the 527 women who had BCS or unilateral mastectomy, 7.4% (n = 39) developed a CBC (DCIS in 12 and invasive cancer in 27). 4.1% (5/122) of women treated with adjuvant endocrine therapy developed a CBC, compared to 8.4% (34/405) who were not treated (p = .11). Features associated with CBC risk were younger age at menarche (adjusted odds ratio [aOR] of 0.76, p = .03) and low nuclear grade of DCIS (aOR of 5.43 for grade 1 versus 3, p = .01). CONCLUSION: In women treated for DCIS, the overall rate of CBC was low at 7.4%. Younger age at menarche and low nuclear grade of DCIS had significant associations with higher CBC risk.

Accuracy of Preoperative Breast MRI Versus Conventional Imaging in Measuring Pathologic Extent of Invasive Lobular Carcinoma.

OBJECTIVE: To determine whether invasive lobular carcinoma (ILC) extent is more accurately depicted with preoperative MRI (pMRI) than conventional imaging (mammography and/or ultrasound). METHODS: After IRB approval, we retrospectively identified women with pMRIs (February 2005 to January 2014) to evaluate pure ILC excluding those with ipsilateral pMRI BI-RADS 4 or 5 findings or who had neoadjuvant chemotherapy. Agreement between imaging and pathology sizes was summarized using Bland-Altman plots, absolute and percent differences, and the intraclass correlation coefficient (ICC). Rates of underestimation and overestimation were evaluated and their associations with clinical features were explored. RESULTS: Among the 56 women included, pMRI demonstrated better agreement with pathology than conventional imaging by mean absolute difference (1.6 mm versus -7.8 mm, P < 0.001), percent difference (10.3% versus -16.4%, P < 0.001), and ICC (0.88 versus 0.61, P = 0.019). Conventional imaging more frequently underestimated ILC span than pMRI using a 5 mm difference threshold (24/56 (43%) versus 10/56 (18%), P < 0.001), a 25% threshold (19/53 (36%) versus 10/53 (19%), P = 0.035), and T category change (17/56 (30%) versus 7/56 (13%), P = 0.006). Imaging-pathology size concordance was greater for MRI-described solitary masses than other lesions for both MRI and conventional imaging (P < 0.05). Variability of conventional imaging was lower for patients ≥ the median age of 62 years than for younger patients (SD: 12 mm versus 22 mm, P = 0.012). CONCLUSION: MRI depicts pure ILC more accurately than conventional imaging and may have particular value for younger women.

Association of Tibial Plateau Fracture Morphology With Ligament Disruption in the Context of Multiligament Knee Injury.

BACKGROUND: We identified common morphologies of tibial plateau fractures that arise with multiligament knee injuries (MLKIs), and investigated the relationship of the fracture with ligament tears. We also evaluated the correlation of 3 tibial plateau fracture classification systems (Schatzker, AO, and Duparc). METHODS: Over a 2-year period, a single orthopaedic surgeon at our institution managed 90 MLKIs. Images of those knees with a tibial plateau fracture were retrospectively reviewed and classified per Schatzker, AO, and Duparc systems. Correlation among the 3 systems was evaluated using Spearman nonparametric correlation coefficient. Associations between fracture grading system and ligament tears were estimated using logistic regression. Associations between ligament tears and tibial plateau fracture location (medial vs lateral) were estimated using exact logistic regression. RESULTS: A total of 19 of 90 knees suffered tibial plateau fractures. There was reasonable correlation among the 3 tibial plateau classification systems. Increasing grade under the Schatzker system showed statistically significant associations with medial collateral ligament (MCL) (P = 0.056) and posterolateral corner (PLC) (P = 0.035) tears. Increasing grade under the Duparc system showed statistically significant associations with MCL (P = 0.032) and PLC (P = 0.058) tears. PLC tears had a statistically significant association with medial plateau fractures (P = 0.003); odds ratio of 121.1 (95% CI: 2.2-∞). MCL tears had a statistically significant association with lateral plateau fractures (P = 0.004); odds ratio of 18.4 (95% CI: 2.1-∞). Although not statistically significant, 8 out of 9 knees with a lateral plateau fracture demonstrated tear of the anterior cruciate ligament (ACL). CONCLUSIONS: As the grade of designation increases within the Schatzker and Duparc tibial plateau fracture classifications, as does the likelihood of MCL and PLC tear. The majority of tibial plateau fractures that occur in the context of MLKI are either isolated to the medial or lateral tibial plateau. Medial tibial plateau fractures are associated with PLC tears. Lateral tibial plateau fractures are associated with MCL tears, and although not statistically significant in our small sample size, 8 out of 9 knees also demonstrated a tear of the ACL.

Clinical-Radiologic Correlation of Extraocular Eye Movement Disorders: Seeing beneath the Surface.

Extraocular eye movement disorders are relatively common and may be a significant source of discomfort and morbidity for patients. The presence of restricted eye movement can be detected clinically with quick, easily performed, noninvasive maneuvers that assess medial, lateral, upward, and downward gaze. However, detecting the presence of ocular dysmotility may not be sufficient to pinpoint the exact cause of eye restriction. Imaging plays an important role in excluding, in some cases, and detecting, in others, a specific cause responsible for the clinical presentation. However, the radiologist should be aware that the imaging findings in many of these conditions when taken in isolation from the clinical history and symptoms are often nonspecific. Normal eye movements are directly controlled by the ocular motor cranial nerves (CN III, IV, and VI) in coordination with indirect input or sensory stimuli derived from other cranial nerves. Specific causes of ocular dysmotility can be localized to the cranial nerve nuclei in the brainstem, the cranial nerve pathways in the peripheral nervous system, and the extraocular muscles in the orbit, with disease at any of these sites manifesting clinically as an eye movement disorder. A thorough understanding of central nervous system anatomy, cranial nerve pathways, and orbital anatomy, as well as familiarity with patterns of eye movement restriction, are necessary for accurate detection of radiologic abnormalities that support a diagnostic source of the suspected extraocular movement disorder. ©RSNA, 2016.

Non-traumatic anterior cruciate ligament abnormalities and their relationship to osteoarthritis using morphological grading and cartilage T2 relaxation times: data from the Osteoarthritis Initiative (OAI).

OBJECTIVES: The aim of this work was to study anterior cruciate ligament (ACL) degeneration in relation to MRI-based morphological knee abnormalities and cartilage T2 relaxation times in subjects with symptomatic osteoarthritis. METHODS: Two radiologists screened the right knee MRI of 304 randomly selected participants in the Osteoarthritis Initiative cohort with symptomatic OA, for ACL abnormalities. Of the 52 knees with abnormalities, 28 had mucoid degeneration, 12 had partially torn ACLs, and 12 had completely torn ACLs. Fifty-three randomly selected subjects with normal ACLs served as controls. Morphological knee abnormalities were graded using the WORMS score. Cartilage was segmented and compartment-specific T2 values were calculated. RESULTS: Compared to normal ACL knees, those with ACL abnormalities had a greater prevalence of, and more severe, cartilage, meniscal, bone marrow, subchondral cyst, and medial collateral ligament lesions (all p < 0.05). T2 measurements did not significantly differ by ACL status. CONCLUSIONS: ACL abnormalities were associated with more severe degenerative changes, likely because of greater joint instability. T2 measurements may not be well suited to assess advanced cartilage degeneration.

Physical activity is associated with magnetic resonance imaging-based knee cartilage T2 measurements in asymptomatic subjects with and those without osteoarthritis risk factors.

OBJECTIVE: To evaluate the association of exercise and knee-bending activities with magnetic resonance imaging (MRI)-based knee cartilage T2 relaxation times and morphologic abnormalities in asymptomatic subjects from the Osteoarthritis Initiative, with or without osteoarthritis (OA) risk factors. METHODS: We studied 128 subjects with knee OA risk factors and 33 normal control subjects ages 45-55 years, with a body mass index of 18-27 kg/m(2) and no knee pain. Subjects were categorized according to exercise level, using the leisure activity component of the Physical Activity Scale for the Elderly, and by self-reported frequent knee-bending activities. Two radiologists graded the cartilage of the right knee on MR images, using the Whole-Organ MRI Score (WORMS). Cartilage was segmented, and compartment-specific T2 values were calculated. Differences between the exercise groups and knee-bending groups were determined using multiple linear and logistic regression models. RESULTS: Among subjects with risk factors for knee OA, light exercisers had lower T2 values compared with sedentary and moderate/strenuous exercisers. When the sexes were analyzed separately, female moderate/strenuous exercisers had higher T2 values compared with sedentary individuals and light exercisers. Subjects without risk factors displayed no significant differences in T2 values according to exercise level. However, frequent knee-bending activities were associated with higher T2 values in both subjects with OA risk factors and those without OA risk factors and with more severe cartilage lesions in the group with risk factors. CONCLUSION: In subjects at risk of knee OA, light exercise was associated with low T2 values, whereas moderate/strenuous exercise in women was associated with high T2 values. Higher T2 values and WORMS grades were also observed in frequent knee-benders, suggesting greater cartilage degeneration in these individuals.