Artificial intelligence in breast imaging: Current situation and clinical challenges.

Breast cancer ranks among the most prevalent malignant tumours and is the primary contributor to cancer-related deaths in women. Breast imaging is essential for screening, diagnosis, and therapeutic surveillance. With the increasing demand for precision medicine, the heterogeneous nature of breast cancer makes it necessary to deeply mine and rationally utilize the tremendous amount of breast imaging information. With the rapid advancement of computer science, artificial intelligence (AI) has been noted to have great advantages in processing and mining of image information. Therefore, a growing number of scholars have started to focus on and research the utility of AI in breast imaging. Here, an overview of breast imaging databases and recent advances in AI research are provided, the challenges and problems in this field are discussed, and then constructive advice is further provided for ongoing scientific developments from the perspective of the National Natural Science Foundation of China.

Differences in Cortical Activation During Dorsiflexion and Plantarflexion in Chronic Ankle Instability: A Task-fMRI Study.

BACKGROUND: Chronic ankle instability is a common sports injury that often presents with increased plantarflexion and restricted dorsiflexion. The cumulative effect of peripheral injuries may induce neuroplasticity in the central nervous system. However, the relationship between dorsiflexion or plantarflexion and the central nervous system in patients with chronic ankle instability remains unknown. QUESTIONS/PURPOSES: (1) Is there a difference in region and voxel (volume pixel) of cortical activation during plantarflexion and dorsiflexion between patients with chronic ankle instability and a control group with normal ankle function? (2) Is there a correlation between activation of sensorimotor-related brain regions and three clinical measurement scales of ankle function and disease severity in patients with chronic ankle instability? METHODS: Between December 2020 and May 2022, we treated 400 patients who had chronic ankle instability. Ten percent (40 patients; mean ± standard deviation age 29 ± 7 years; 17 male patients) were randomly selected to participate in this study. We recruited 42 volunteers with normal ankle function (mean age 28 ± 5 years; 21 male participants) matched by age and education level. A total of 2.5% (1 of 40) of patients with bilateral chronic ankle instability and 30% (12 of 40) with left-sided chronic ankle injury did not meet our inclusion criteria and were excluded from the study. The control group underwent MRI with good image quality. Finally, 27 patients with chronic ankle instability (mean age 26 ± 5 years; 10 male patients) and 42 participants with normal ankle function were enrolled. Ankle function and disease severity were assessed using three clinical scales: the Cumberland Ankle Instability Tool, Karlsson-Peterson Ankle Function Score, and the American Orthopedic Foot and Ankle Society Score. A uniplanar and nonweightbearing ankle dorsiflexion-plantarflexion paradigm (a recognized model or pattern) was performed using a short-block design during the functional MRI scan. This experimental design included a series of on-off periods consisting of movement and a rest period. From 15° of plantarflexion to 15° of dorsiflexion, the manipulator allowed 30° of ankle rotation. The cerebral excitability patterns between patients with chronic ankle instability and controls were analyzed using t-tests. We retained voxels with p values less than 0.05 in a voxel-level family-wise error correction. Clusters with voxel numbers greater than 10 were retained. The Cohen d coefficient was used to calculate between-group effect sizes. Spearman analysis was performed to explore the correlation between activation regions and the three clinical assessment scales. RESULTS: In the patient group, cortical activation was greater during plantarflexion than during dorsiflexion, which was different from that in the control group. The between-group comparison showed that patients with chronic ankle instability had reduced activation in the ipsilateral precuneus (cluster size = 35 voxels [95% CI -0.23 to 0.07]; p < 0.001) during dorsiflexion, whereas during plantarflexion, chronic ankle instability caused increased activation in the ipsilateral superior temporal gyrus (cluster size = 90 voxels [95% CI -0.73 to -0.13]; p < 0.001), precuneus (cluster size = 18 voxels [95% CI -0.56 to -0.19]; p < 0.001), supplementary motor area (cluster size = 57 voxels [95% CI -0.31 to 0.00]; p < 0.001), superior frontal gyrus (cluster size = 43 voxels [95% CI -0.82 to -0.29]; p < 0.001), medial part of the superior frontal gyrus (cluster size = 39 voxels [95% CI 0.41 to 0.78]; p < 0.001), and contralateral postcentral gyrus (cluster size = 100 voxels [95% CI -0.32 to 0.02]; p < 0.001). Patients with chronic ankle instability showed a large effect size compared with controls (Cohen d > 0.8). During plantarflexion, the number of activated voxels in the supplementary motor area had a modest, positive correlation with the Karlsson-Peterson Ankle Function Score (r = 0.52; p = 0.01), and the number of activated voxels in the primary motor cortex (M1) and primary sensory cortex (S1) had a weak, positive correlation with the American Orthopedic Foot and Ankle Society Score in patients with chronic ankle instability (M1: r = 0.45; p = 0.02, S1: r = 0.49; p = 0.01). CONCLUSION: Compared with volunteers with normal ankle function, patients with chronic ankle instability had increased cortical activation during plantarflexion and decreased cortical activation during dorsiflexion. We analyzed the central neural mechanisms of chronic ankle instability in patients with sports injuries and provided a theoretical basis for the development of new central and peripheral interventions in the future. CLINICAL RELEVANCE: Because there was a positive correlation between the neural activity in sensorimotor-related regions during plantarflexion and clinical severity, clinicians might one day be able to help patients who have chronic ankle instability with neuromuscular rehabilitation by applying electrical stimulation to specific targets (such as S1M1 and the supplementary motor area) or by increasing activation of sensorimotor neurons through ankle movement.

Solitary Fibrous Tumor of the Spine: Imaging Grading Diagnosis and Prognosis.

OBJECTIVE: This study aimed to investigate the imaging features and prognosis of spinal solitary fibrous tumors (SFTs) of different pathological grades. METHODS: The clinical features, computed tomography and magnetic resonance (MR) images, and follow-up data of 23 patients with SFTs were reviewed. The patients were divided into 3 groups according to their pathological manifestations: grade 1 (n = 3), grade 2 (n = 14), and grade 3 (n = 6). The following imaging features were recorded: location, computed tomography density/MR intensity, enhancement pattern, dural tail sign, adjacent bone remodeling, lobulation, and tumor size. The immunohistochemical (Ki-67/MIB-1) levels were also investigated. All parameters were statistically analyzed between grade 2 and 3 tumors. RESULTS: The Ki-67/MIB-1 index was markedly higher in grade 3 tumors than in grade 2 tumors ( P < 0.001). All grade 1 lesions appeared hypointense on T2-weighted image, whereas grade 2 and 3 lesions appeared isointense or mildly hyperintense. There were significant differences in enhancement type and osteolytic bony destruction between grade 2 and 3 tumors ( P < 0.05). However, no marked differences were found in the distribution of age, sex, location, MR signal, degree of enhancement, compressive bony absorption, dural tail sign, or maximum vertical/traverse diameter ratio. Malignant progression occurred less frequently in patients with grade 2 tumors than in those with grade 3 tumors, but the difference was not statistically significant. CONCLUSIONS: Different grades of spinal SFTs have different degrees of proliferation and imaging features, especially grade 3 tumors, which show a heterogeneous enhancement pattern, osteolytic bony destruction, and a higher possibility of recurrence and metastasis.

Not Only in Sensorimotor Network: Local and Distant Cerebral Inherent Activity of Chronic Ankle Instability-A Resting-State fMRI Study.

BACKGROUND: Increasing evidence has proved that chronic ankle instability (CAI) is highly related to the central nervous system (CNS). However, it is still unclear about the inherent cerebral activity among the CAI patients. PURPOSE: To investigate the differences of intrinsic functional cerebral activity between the CAI patients and healthy controls (HCs) and further explore its correlation with clinical measurement in CAI patients. MATERIALS AND METHODS: A total of 25 CAI patients and 39 HCs were enrolled in this study. Resting-state functional magnetic resonance imaging (rs-fMRI) was used to detect spontaneous cerebral activity. The metrics of amplitude of low-frequency fluctuation (ALFF), fractional ALFF (fALFF), and regional homogeneity (ReHo) of the two groups were compared by two-sample t-test. The brain regions that demonstrated altered functional metrics were selected as the regions of interest (ROIs). The functional connectivity (FC) was analyzed based on the ROIs. The Spearman correlation was calculated between rs-fMRI metrics and clinical scale scores. RESULTS: Compared with HCs, CAI patients showed higher ALFF and ReHo values in the right postcentral gyrus, the right precentral gyrus, and the right middle frontal gyrus, while lower fALFF values in the orbital-frontal cortex (OFC, p < 0.01 after correction). Increasing FC between the right precentral gyrus and the right postcentral gyrus while decreasing FC between the right precentral gyrus and the anterior cingulum cortex (ACC), the right middle frontal gyrus and the left middle temporal gyrus, and the OFC and left inferior parietal lobule (IPL) was observed. In addition, in the CAI group, the ReHo value negatively correlated with the Cumberland Ankle Instability Tool score in the right middle frontal gyrus (r = -0.52, p = 0.007). CONCLUSION: The CAI patients exhibited enhanced and more coherent regional inherent neuronal activity within the sensorimotor network while lower regional inherent activity in pain/emotion modulation related region. In addition, the information exchanges were stronger within the sensorimotor network while weaker between distant interhemispheric regions. Besides, the increased inherent activity in the right middle frontal gyrus was related to clinical severity. These findings may provide insights into the pathophysiological alteration in CNS among CAI patients.

Microstructural Alteration of Lumbosacral Nerve Roots in Chronic Inflammatory Demyelinating Polyradiculoneuropathy: Insights From DTI and Correlations with Electrophysiological Parameters.

RATIONALE AND OBJECTIVES: To detect the diffusion characteristics of lumbosacral nerve roots in patients with chronic inflammatory demyelinating polyradiculoneuropathy (CIDP) and further to explore their correlations with electrophysiological parameters of lower extremity nerves. MATERIALS AND METHODS: Eighteen CIDP patients and 18 age and sex-matched healthy volunteers were enrolled in this study from August 2019 to August 2020. Axial diffusion tensor imaging (DTI) of lumbosacral plexus was performed in all subjects and fractional anisotropy (FA), axial diffusivity (AD), radial diffusivity (RD), and mean diffusivity (MD) of lumbosacral nerve roots were measured. Two-sample t test or Mann-Whitney U test was used to compare the difference of DTI parameters between two groups. Receiver operating characteristic curves were plotted to determine the diagnostic accuracy. All patients also underwent nerve conduction studies. Correlations between DTI parameters of lumbosacral nerve roots and electrophysiological parameters were analyzed with Pearson or Spearman coefficients. RESULTS: CIDP patients showed significantly lower FA as well as higher AD, RD, and MD values of lumbosacral nerve roots (FA:0.24±0.054, 0.32±0.044; AD:2.31±0.256, 2.11±0.230 (×10-3mm2/s); RD:1.28±0.189, 1.13±0.106 (×10-3mm2/s); MD:1.68±0.268, 1.45±0.186 (×10-3mm2/s) in CIDP and control group, respectively, all p < 0.05). Receiver operating characteristic analysis showed among all DTI parameters, FA had the best diagnostic accuracy with an area under the curve of 0.914 and optimal cut-off value of 0.27. FA showed a positive correlation while RD showed a negative correlation with a conduction velocity of tibial and common peroneal nerves. RD also correlated positively with F-wave minimal latency of tibial nerves. CONCLUSION: DTI can be used to assess the microstructure alterations of lumbosacral nerve roots in CIDP patients. FA and RD may serve as potential markers reflecting the conduction function of tibial and common peroneal nerves.