Artificial Intelligence for Automated Implant Identification in Total Hip Arthroplasty: A Multicenter External Validation Study Exceeding Two Million Plain Radiographs.

BACKGROUND: The surgical management of complications after total hip arthroplasty (THA) necessitates accurate identification of the femoral implant manufacturer and model. Automated image processing using deep learning has been previously developed and internally validated; however, external validation is necessary prior to responsible application of artificial intelligence (AI)-based technologies. METHODS: We trained, validated, and externally tested a deep learning system to classify femoral-sided THA implants as one of the 8 models from 2 manufacturers derived from 2,954 original, deidentified, retrospectively collected anteroposterior plain radiographs across 3 academic referral centers and 13 surgeons. From these radiographs, 2,117 were used for training, 249 for validation, and 588 for external testing. Augmentation was applied to the training set (n = 2,117,000) to increase model robustness. Performance was evaluated by area under the receiver operating characteristic curve, sensitivity, specificity, and accuracy. Implant identification processing speed was calculated. RESULTS: The training and testing sets were drawn from statistically different populations of implants (P < .001). After 1,000 training epochs by the deep learning system, the system discriminated 8 implant models with a mean area under the receiver operating characteristic curve of 0.991, accuracy of 97.9%, sensitivity of 88.6%, and specificity of 98.9% in the external testing dataset of 588 anteroposterior radiographs. The software classified implants at a mean speed of 0.02 seconds per image. CONCLUSION: An AI-based software demonstrated excellent internal and external validation. Although continued surveillance is necessary with implant library expansion, this software represents responsible and meaningful clinical application of AI with immediate potential to globally scale and assist in preoperative planning prior to revision THA.

Premature synaptic mitochondrial dysfunction in the hippocampus during aging contributes to memory loss.

Aging is a process characterized by cognitive impairment and mitochondrial dysfunction. In neurons, these organelles are classified as synaptic and non-synaptic mitochondria depending on their localization. Interestingly, synaptic mitochondria from the cerebral cortex accumulate more damage and are more sensitive to swelling than non-synaptic mitochondria. The hippocampus is fundamental for learning and memory, synaptic processes with high energy demand. However, it is unknown if functional differences are found in synaptic and non-synaptic hippocampal mitochondria; and whether this could contribute to memory loss during aging. In this study, we used 3, 6, 12 and 18 month-old (mo) mice to evaluate hippocampal memory and the function of both synaptic and non-synaptic mitochondria. Our results indicate that recognition memory is impaired from 12mo, whereas spatial memory is impaired at 18mo. This was accompanied by a differential function of synaptic and non-synaptic mitochondria. Interestingly, we observed premature dysfunction of synaptic mitochondria at 12mo, indicated by increased ROS generation, reduced ATP production and higher sensitivity to calcium overload, an effect that is not observed in non-synaptic mitochondria. In addition, at 18mo both mitochondrial populations showed bioenergetic defects, but synaptic mitochondria were prone to swelling than non-synaptic mitochondria. Finally, we treated 2, 11, and 17mo mice with MitoQ or Curcumin (Cc) for 5 weeks, to determine if the prevention of synaptic mitochondrial dysfunction could attenuate memory loss. Our results indicate that reducing synaptic mitochondrial dysfunction is sufficient to decrease age-associated cognitive impairment. In conclusion, our results indicate that age-related alterations in ATP produced by synaptic mitochondria are correlated with decreases in spatial and object recognition memory and propose that the maintenance of functional synaptic mitochondria is critical to prevent memory loss during aging.

Detection of changes in mitochondrial hydrogen sulfide i n vivo in the fish model Poecilia mexicana (Poeciliidae).

In this paper, we outline the use of a mitochondria-targeted ratiometric mass spectrometry probe, MitoA, to detect in vivo changes in mitochondrial hydrogen sulfide (H2S) in Poecilia mexicana (family Poeciliidae). MitoA is introduced via intraperitoneal injection into the animal and is taken up by mitochondria, where it reacts with H2S to form the product MitoN. The MitoN/MitoA ratio can be used to assess relative changes in the amounts of mitochondrial H2S produced over time. We describe the use of MitoA in the fish species P. mexicana to illustrate the steps for adopting the use of MitoA in a new organism, including extraction and purification of MitoA and MitoN from tissues followed by tandem mass spectrometry. In this proof-of-concept study we exposed H2S tolerant P. mexicana to 59 µM free H2S for 5 h, which resulted in increased MitoN/MitoA in brain and gills, but not in liver or muscle, demonstrating increased mitochondrial H2S levels in select tissues following whole-animal H2S exposure. This is the first time that accumulation of H2S has been observed in vivo during whole-animal exposure to free H2S using MitoA. This article has an associated First Person interview with the first author of the paper.

Neuroprotective effects of the mitochondria-targeted antioxidant MitoQ in a model of inherited amyotrophic lateral sclerosis.

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disorder characterized by motor neuron degeneration that ultimately results in progressive paralysis and death. Growing evidence indicates that mitochondrial dysfunction and oxidative stress contribute to motor neuron degeneration in ALS. To further explore the hypothesis that mitochondrial dysfunction and nitroxidative stress contribute to disease pathogenesis at the in vivo level, we assessed whether the mitochondria-targeted antioxidant [10-(4,5-dimethoxy-2-methyl-3,6-dioxo-1,4-cyclohexadien-1-yl)decyl]triphenylphosphonium methane sulfonate (MitoQ) can modify disease progression in the SOD1(G93A) mouse model of ALS. To do this, we administered MitoQ (500 µM) in the drinking water of SOD1(G93A) mice from a time when early symptoms of neurodegeneration become evident at 90 days of age until death. This regime is a clinically plausible scenario and could be more easily translated to patients as this corresponds to initiating treatment of patients after they are first diagnosed with ALS. MitoQ was detected in all tested tissues by liquid chromatography/mass spectrometry after 20 days of administration. MitoQ treatment slowed the decline of mitochondrial function, in both the spinal cord and the quadriceps muscle, as measured by high-resolution respirometry. Importantly, nitroxidative markers and pathological signs in the spinal cord of MitoQ-treated animals were markedly reduced and neuromuscular junctions were recovered associated with a significant increase in hindlimb strength. Finally, MitoQ treatment significantly prolonged the life span of SOD1(G93A) mice. Our results support a role for mitochondrial nitroxidative damage and dysfunction in the pathogenesis of ALS and suggest that mitochondria-targeted antioxidants may be of pharmacological use for ALS treatment.